Analyses - Random Forests v1
Joey Hulbert
10/11/2021
Purpose
The purpose of this analysis document is to ensure the reproducability of the results by guiding the reader through the random forest analysis of the factors associated with the health of western redcedar.
Approach
Root data were shared by citizen scientists in the Wester Redcedar Dieback Map project on iNaturalist.
- These data were then combined with
- Climate data derived using the ClimateNA tool. Instructions for how this tool was used are included in the climate subfolder.
- Topographic data extraced from DEM rasters. Preliminary methods for extracting topo data from GPS points are available in the topo subfolder.
- Soils data downloaded from gSSURRGO databases for Washington and Oregon. Instructions for extracting the soils data using Arc GIS Pro are included in the soils subfolder.
All of the data used in the below analyses are described in the Data Wrangle folder.
Limitations
- Below are some limitations to these results to clarify
- representation of the data were heavily biased to the western side of Washington and Oregon (west of the Cascades).
Next steps
- Do following before next commit
- calculate better topographic variables (aspect, and those that combine both topo and climate data?)
- look into what is happening with -9999 values in components
Data
The data used in the below visualizations are described in the Data Wrangle folder.
All tree health categories
## # A tibble: 11 x 2
## # Groups: field.tree.canopy.symptoms [11]
## field.tree.canopy.symptoms n
## <fct> <int>
## 1 Branch Dieback or 'Flagging' 19
## 2 Browning Canopy 19
## 3 Extra Cone Crop 2
## 4 Healthy 403
## 5 Multiple Symptoms (please list in Notes) 17
## 6 New Dead Top (red or brown needles still attached) 33
## 7 Old Dead Top (needles already gone) 83
## 8 Other (please describe in Notes) 8
## 9 Thinning Canopy 118
## 10 Tree is dead 37
## 11 Yellowing Canopy 10Filter Data
We need to filter the data to only include response and explanatory variables we’re interested in. For example, whether a sound clip was included in the iNat data is not important.
We also need to remove other response variables like “field.percent.canopy.affected….” so it is not used as a predictor for tree health.
Note it might be interesting to know if the user was an important factor in predicting if the tree is healthy/unhealthy.
There are also a number of factors that should probably be removed because they may be biasing the data. For example, only trees with the ‘other factor’ question may only be answered for unhealthy trees. We need to think about this a bit more.
Impute data
We continue to get the below error, but were able to work around it by imputing the data.
Error in randomForest.default(m, y, …) : Need at least two classes to do classification.
To impute the data we have to remove factors with >53 levels.
The below code lists the number of levels for the variables that are factors.
- The following factors had more than 53 levels
- “muaggatt_musym”
- “muaggatt_muname”
- “component_compname”
- “component_geomdesc”
- “component_taxclname”
- “component_taxsubgrp”
Imputed data table
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 46.46% 94.74% 94.74%100.00% 17.12% 70.59% 87.88% 75.90%100.00% 71.19% 94.59%100.00%
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 45.79% 94.74% 94.74%100.00% 14.89% 70.59% 87.88% 77.11%100.00% 73.73% 94.59%100.00%
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 44.99% 94.74%100.00%100.00% 14.14% 70.59% 87.88% 75.90%100.00% 72.03% 91.89%100.00%
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 45.53% 94.74%100.00%100.00% 14.14% 82.35% 87.88% 75.90%100.00% 72.88% 94.59%100.00%
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 45.66% 94.74% 94.74%100.00% 16.13% 76.47% 87.88% 72.29%100.00% 70.34% 97.30%100.00%
## ntree OOB 1 2 3 4 5 6 7 8 9 10 11
## 300: 45.53% 94.74%100.00%100.00% 15.38% 76.47% 87.88% 73.49%100.00% 71.19% 94.59%100.00%Train and test data
Model
##
## Call:
## randomForest(formula = field.tree.canopy.symptoms ~ ., data = training, ntree = 2001, importance = TRUE, proximity = TRUE, na.action = na.omit)
## Type of random forest: classification
## Number of trees: 2001
## No. of variables tried at each split: 23
##
## OOB estimate of error rate: 47.95%
## Confusion matrix:
## Branch Dieback or 'Flagging'
## Branch Dieback or 'Flagging' 1
## Browning Canopy 0
## Extra Cone Crop 0
## Healthy 3
## Multiple Symptoms (please list in Notes) 0
## New Dead Top (red or brown needles still attached) 0
## Old Dead Top (needles already gone) 0
## Other (please describe in Notes) 0
## Thinning Canopy 2
## Tree is dead 0
## Yellowing Canopy 0
## Browning Canopy
## Branch Dieback or 'Flagging' 0
## Browning Canopy 1
## Extra Cone Crop 0
## Healthy 1
## Multiple Symptoms (please list in Notes) 1
## New Dead Top (red or brown needles still attached) 2
## Old Dead Top (needles already gone) 0
## Other (please describe in Notes) 0
## Thinning Canopy 0
## Tree is dead 3
## Yellowing Canopy 0
## Extra Cone Crop Healthy
## Branch Dieback or 'Flagging' 0 11
## Browning Canopy 0 10
## Extra Cone Crop 0 1
## Healthy 0 252
## Multiple Symptoms (please list in Notes) 0 10
## New Dead Top (red or brown needles still attached) 0 13
## Old Dead Top (needles already gone) 0 22
## Other (please describe in Notes) 0 6
## Thinning Canopy 0 36
## Tree is dead 0 18
## Yellowing Canopy 0 5
## Multiple Symptoms (please list in Notes)
## Branch Dieback or 'Flagging' 0
## Browning Canopy 0
## Extra Cone Crop 0
## Healthy 2
## Multiple Symptoms (please list in Notes) 2
## New Dead Top (red or brown needles still attached) 0
## Old Dead Top (needles already gone) 1
## Other (please describe in Notes) 0
## Thinning Canopy 0
## Tree is dead 0
## Yellowing Canopy 0
## New Dead Top (red or brown needles still attached)
## Branch Dieback or 'Flagging' 0
## Browning Canopy 2
## Extra Cone Crop 0
## Healthy 5
## Multiple Symptoms (please list in Notes) 0
## New Dead Top (red or brown needles still attached) 2
## Old Dead Top (needles already gone) 2
## Other (please describe in Notes) 0
## Thinning Canopy 2
## Tree is dead 2
## Yellowing Canopy 1
## Old Dead Top (needles already gone)
## Branch Dieback or 'Flagging' 2
## Browning Canopy 0
## Extra Cone Crop 1
## Healthy 10
## Multiple Symptoms (please list in Notes) 1
## New Dead Top (red or brown needles still attached) 4
## Old Dead Top (needles already gone) 15
## Other (please describe in Notes) 0
## Thinning Canopy 13
## Tree is dead 4
## Yellowing Canopy 1
## Other (please describe in Notes)
## Branch Dieback or 'Flagging' 0
## Browning Canopy 0
## Extra Cone Crop 0
## Healthy 1
## Multiple Symptoms (please list in Notes) 0
## New Dead Top (red or brown needles still attached) 0
## Old Dead Top (needles already gone) 0
## Other (please describe in Notes) 0
## Thinning Canopy 0
## Tree is dead 0
## Yellowing Canopy 0
## Thinning Canopy Tree is dead
## Branch Dieback or 'Flagging' 2 0
## Browning Canopy 0 3
## Extra Cone Crop 0 0
## Healthy 17 9
## Multiple Symptoms (please list in Notes) 0 0
## New Dead Top (red or brown needles still attached) 2 1
## Old Dead Top (needles already gone) 15 4
## Other (please describe in Notes) 0 0
## Thinning Canopy 19 8
## Tree is dead 4 0
## Yellowing Canopy 2 0
## Yellowing Canopy class.error
## Branch Dieback or 'Flagging' 0 0.9375000
## Browning Canopy 0 0.9375000
## Extra Cone Crop 0 1.0000000
## Healthy 1 0.1627907
## Multiple Symptoms (please list in Notes) 0 0.8571429
## New Dead Top (red or brown needles still attached) 1 0.9200000
## Old Dead Top (needles already gone) 0 0.7457627
## Other (please describe in Notes) 0 1.0000000
## Thinning Canopy 2 0.7682927
## Tree is dead 0 1.0000000
## Yellowing Canopy 0 1.0000000
Concerns
- Below are some concerns that should be investigated
- The error rate is pretty high (~35%)
- The MDS plots only represent a small percentage of the
Questions
- Below are some questions to resolve moving forward
- What is difference between MeanDecreaseAccuracy ad MeanDecreaseGini
- MeanDecreaseAccuracy - how much the factor affected classification trees across, averaged for all 2000 trees?
- MeanDecreaseGini - variation in influence of factor compared to other factors?
- What is difference between MeanDecreaseAccuracy ad MeanDecreaseGini
Explore different groupings
Five filtered Symptoms
Selected tree health categories
## # A tibble: 5 x 2
## # Groups: field.tree.canopy.symptoms [5]
## field.tree.canopy.symptoms n
## <fct> <int>
## 1 Healthy 403
## 2 New Dead Top (red or brown needles still attached) 33
## 3 Old Dead Top (needles already gone) 83
## 4 Thinning Canopy 118
## 5 Tree is dead 37Train and test data
Try creating random forest model from training data
##
## Call:
## randomForest(formula = field.tree.canopy.symptoms ~ ., data = training, ntree = 2001, importance = TRUE, proximity = TRUE, na.action = na.omit)
## Type of random forest: classification
## Number of trees: 2001
## No. of variables tried at each split: 23
##
## OOB estimate of error rate: 41.98%
## Confusion matrix:
## Healthy
## Healthy 252
## New Dead Top (red or brown needles still attached) 16
## Old Dead Top (needles already gone) 21
## Thinning Canopy 46
## Tree is dead 13
## New Dead Top (red or brown needles still attached)
## Healthy 4
## New Dead Top (red or brown needles still attached) 5
## Old Dead Top (needles already gone) 2
## Thinning Canopy 0
## Tree is dead 3
## Old Dead Top (needles already gone)
## Healthy 17
## New Dead Top (red or brown needles still attached) 3
## Old Dead Top (needles already gone) 22
## Thinning Canopy 24
## Tree is dead 8
## Thinning Canopy Tree is dead
## Healthy 17 5
## New Dead Top (red or brown needles still attached) 1 2
## Old Dead Top (needles already gone) 18 3
## Thinning Canopy 13 4
## Tree is dead 5 1
## class.error
## Healthy 0.1457627
## New Dead Top (red or brown needles still attached) 0.8148148
## Old Dead Top (needles already gone) 0.6666667
## Thinning Canopy 0.8505747
## Tree is dead 0.9666667
Binary symptoms
Binary tree health categories
## # A tibble: 2 x 2
## # Groups: field.tree.canopy.symptoms [2]
## field.tree.canopy.symptoms n
## <fct> <int>
## 1 Healthy 403
## 2 Unhealthy 346Train and test data
Try creating random forest model from training data
##
## Call:
## randomForest(formula = field.tree.canopy.symptoms ~ ., data = training, ntree = 2001, importance = TRUE, proximity = TRUE, na.action = na.omit)
## Type of random forest: classification
## Number of trees: 2001
## No. of variables tried at each split: 23
##
## OOB estimate of error rate: 28.52%
## Confusion matrix:
## Healthy Unhealthy class.error
## Healthy 216 83 0.2775920
## Unhealthy 77 185 0.2938931
## left daughter right daughter split var split point status
## 1 2 3 norm_Tmin02 2.150000e+00 1
## 2 4 5 DD_18_at 7.750000e+02 1
## 3 6 7 muaggatt_brockdepmin 8.090696e+00 1
## 4 8 9 norm_Eref_sm 3.135000e+02 1
## 5 10 11 norm_RH_sp 7.250000e+01 1
## 6 12 13 norm_DD18_sm 6.000000e+01 1
## 7 14 15 DD_0_wt 5.150000e+01 1
## 8 16 17 norm_DD_18_11 3.485000e+02 1
## 9 18 19 component_taxpartsize 2.642073e+08 1
## 10 20 21 norm_Eref_at 1.115000e+02 1
## 11 0 0 <NA> 0.000000e+00 -1
## 12 22 23 component_slopelenusle_h 7.783250e+01 1
## 13 24 25 PPT08 2.150000e+01 1
## 14 26 27 norm_CMI01 1.195000e+01 1
## 15 28 29 norm_CMI05 -1.295000e+00 1
## 16 0 0 <NA> 0.000000e+00 -1
## 17 0 0 <NA> 0.000000e+00 -1
## 18 30 31 component_aspectrep 4.955931e+01 1
## 19 0 0 <NA> 0.000000e+00 -1
## 20 32 33 muaggatt_aws0150wta 1.306160e+01 1
## 21 34 35 muaggatt_hydgrpdcd 2.000000e+00 1
## 22 0 0 <NA> 0.000000e+00 -1
## 23 0 0 <NA> 0.000000e+00 -1
## 24 0 0 <NA> 0.000000e+00 -1
## 25 36 37 norm_EMT -1.175000e+01 1
## 26 38 39 norm_EMT -1.155000e+01 1
## 27 40 41 component_taxgrtgroup 2.814747e+14 1
## 28 42 43 RH_wt 8.100000e+01 1
## 29 44 45 Tmin05 9.050000e+00 1
## 30 46 47 CMI02 2.340500e+01 1
## 31 48 49 norm_Tmin01 5.500000e-01 1
## 32 0 0 <NA> 0.000000e+00 -1
## 33 0 0 <NA> 0.000000e+00 -1
## 34 0 0 <NA> 0.000000e+00 -1
## 35 0 0 <NA> 0.000000e+00 -1
## 36 0 0 <NA> 0.000000e+00 -1
## 37 0 0 <NA> 0.000000e+00 -1
## 38 50 51 norm_CMI04 3.005000e+00 1
## 39 0 0 <NA> 0.000000e+00 -1
## 40 52 53 norm_PPT05 6.700000e+01 1
## 41 54 55 DD_18 2.313500e+03 1
## 42 0 0 <NA> 0.000000e+00 -1
## 43 0 0 <NA> 0.000000e+00 -1
## 44 56 57 norm_SHM 1.125500e+02 1
## 45 0 0 <NA> 0.000000e+00 -1
## 46 58 59 norm_DD5_04 1.425000e+02 1
## 47 60 61 component_elev_h 4.602575e+02 1
## 48 0 0 <NA> 0.000000e+00 -1
## 49 62 63 muaggatt_urbrecptwta 9.600000e-01 1
## 50 0 0 <NA> 0.000000e+00 -1
## 51 64 65 Aspect.x 2.727788e+02 1
## 52 66 67 norm_NFFD_sp 8.450000e+01 1
## 53 68 69 norm_DD5 2.762500e+03 1
## 54 0 0 <NA> 0.000000e+00 -1
## 55 70 71 Tave10 1.165000e+01 1
## 56 72 73 Profilecurv.x 5.323393e-03 1
## 57 74 75 norm_DD_18_10 1.835000e+02 1
## 58 76 77 muaggatt_aws0100wta 2.136000e+01 1
## 59 78 79 DD5_10 1.995000e+02 1
## 60 80 81 component_elev_r 1.170000e+02 1
## 61 0 0 <NA> 0.000000e+00 -1
## 62 82 83 norm_CMD 2.295000e+02 1
## 63 84 85 component_corsteel 3.000000e+00 1
## 64 86 87 component_map_r 9.803530e+02 1
## 65 0 0 <NA> 0.000000e+00 -1
## 66 0 0 <NA> 0.000000e+00 -1
## 67 0 0 <NA> 0.000000e+00 -1
## 68 88 89 norm_CMI01 1.494500e+01 1
## 69 0 0 <NA> 0.000000e+00 -1
## 70 0 0 <NA> 0.000000e+00 -1
## 71 90 91 MAP 2.524000e+03 1
## 72 0 0 <NA> 0.000000e+00 -1
## 73 0 0 <NA> 0.000000e+00 -1
## 74 0 0 <NA> 0.000000e+00 -1
## 75 0 0 <NA> 0.000000e+00 -1
## 76 92 93 norm_PPT06 9.450000e+01 1
## 77 94 95 norm_Eref11 1.650000e+01 1
## 78 0 0 <NA> 0.000000e+00 -1
## 79 96 97 muaggatt_aws050wta 9.250000e+00 1
## 80 0 0 <NA> 0.000000e+00 -1
## 81 98 99 muaggatt_wtdepannmin 6.532635e+01 1
## 82 0 0 <NA> 0.000000e+00 -1
## 83 100 101 Tmin12 9.000000e-01 1
## 84 0 0 <NA> 0.000000e+00 -1
## 85 0 0 <NA> 0.000000e+00 -1
## 86 0 0 <NA> 0.000000e+00 -1
## 87 102 103 norm_DD_18_sm 1.435000e+02 1
## 88 0 0 <NA> 0.000000e+00 -1
## 89 0 0 <NA> 0.000000e+00 -1
## 90 104 105 muaggatt_engstafml 4.000000e+00 1
## 91 0 0 <NA> 0.000000e+00 -1
## 92 106 107 norm_EMT -1.275000e+01 1
## 93 0 0 <NA> 0.000000e+00 -1
## 94 0 0 <NA> 0.000000e+00 -1
## 95 108 109 DD18_09 2.150000e+01 1
## 96 110 111 norm_PPT07 1.850000e+01 1
## 97 112 113 component_wei 5.636787e+01 1
## 98 0 0 <NA> 0.000000e+00 -1
## 99 114 115 norm_Tmin08 1.185000e+01 1
## 100 116 117 CMI_wt 9.454500e+01 1
## 101 0 0 <NA> 0.000000e+00 -1
## 102 0 0 <NA> 0.000000e+00 -1
## 103 118 119 NFFD12 2.150000e+01 1
## 104 120 121 Eref01 1.650000e+01 1
## 105 122 123 component_irrcapscl 2.000000e+00 1
## 106 124 125 component_irrcapcl 3.931599e+00 1
## 107 126 127 norm_CMI 4.032000e+01 1
## 108 0 0 <NA> 0.000000e+00 -1
## 109 0 0 <NA> 0.000000e+00 -1
## 110 0 0 <NA> 0.000000e+00 -1
## 111 128 129 norm_MAP 1.099500e+03 1
## 112 130 131 norm_DD_18_wt 1.152000e+03 1
## 113 0 0 <NA> 0.000000e+00 -1
## 114 0 0 <NA> 0.000000e+00 -1
## 115 0 0 <NA> 0.000000e+00 -1
## 116 0 0 <NA> 0.000000e+00 -1
## 117 0 0 <NA> 0.000000e+00 -1
## 118 0 0 <NA> 0.000000e+00 -1
## 119 0 0 <NA> 0.000000e+00 -1
## 120 0 0 <NA> 0.000000e+00 -1
## 121 0 0 <NA> 0.000000e+00 -1
## 122 132 133 muaggatt_engdwbll 4.000000e+00 1
## 123 0 0 <NA> 0.000000e+00 -1
## 124 134 135 norm_CMI04 6.555000e+00 1
## 125 136 137 NFFD_wt 4.050000e+01 1
## 126 0 0 <NA> 0.000000e+00 -1
## 127 0 0 <NA> 0.000000e+00 -1
## 128 0 0 <NA> 0.000000e+00 -1
## 129 138 139 norm_PPT11 2.205000e+02 1
## 130 0 0 <NA> 0.000000e+00 -1
## 131 140 141 Profilecurv.x -1.090274e-03 1
## 132 0 0 <NA> 0.000000e+00 -1
## 133 142 143 DD5_wt 1.625000e+02 1
## 134 0 0 <NA> 0.000000e+00 -1
## 135 144 145 norm_PAS03 2.500000e+00 1
## 136 0 0 <NA> 0.000000e+00 -1
## 137 0 0 <NA> 0.000000e+00 -1
## 138 0 0 <NA> 0.000000e+00 -1
## 139 0 0 <NA> 0.000000e+00 -1
## 140 0 0 <NA> 0.000000e+00 -1
## 141 146 147 norm_DD_18_03 3.075000e+02 1
## 142 0 0 <NA> 0.000000e+00 -1
## 143 0 0 <NA> 0.000000e+00 -1
## 144 0 0 <NA> 0.000000e+00 -1
## 145 0 0 <NA> 0.000000e+00 -1
## 146 148 149 muaggatt_brockdepmin 1.012805e+02 1
## 147 0 0 <NA> 0.000000e+00 -1
## 148 0 0 <NA> 0.000000e+00 -1
## 149 0 0 <NA> 0.000000e+00 -1
## prediction
## 1 <NA>
## 2 <NA>
## 3 <NA>
## 4 <NA>
## 5 <NA>
## 6 <NA>
## 7 <NA>
## 8 <NA>
## 9 <NA>
## 10 <NA>
## 11 Unhealthy
## 12 <NA>
## 13 <NA>
## 14 <NA>
## 15 <NA>
## 16 Healthy
## 17 Unhealthy
## 18 <NA>
## 19 Healthy
## 20 <NA>
## 21 <NA>
## 22 Healthy
## 23 Unhealthy
## 24 Unhealthy
## 25 <NA>
## 26 <NA>
## 27 <NA>
## 28 <NA>
## 29 <NA>
## 30 <NA>
## 31 <NA>
## 32 Healthy
## 33 Unhealthy
## 34 Unhealthy
## 35 Healthy
## 36 Unhealthy
## 37 Healthy
## 38 <NA>
## 39 Unhealthy
## 40 <NA>
## 41 <NA>
## 42 Unhealthy
## 43 Healthy
## 44 <NA>
## 45 Unhealthy
## 46 <NA>
## 47 <NA>
## 48 Unhealthy
## 49 <NA>
## 50 Healthy
## 51 <NA>
## 52 <NA>
## 53 <NA>
## 54 Unhealthy
## 55 <NA>
## 56 <NA>
## 57 <NA>
## 58 <NA>
## 59 <NA>
## 60 <NA>
## 61 Healthy
## 62 <NA>
## 63 <NA>
## 64 <NA>
## 65 Healthy
## 66 Unhealthy
## 67 Healthy
## 68 <NA>
## 69 Healthy
## 70 Unhealthy
## 71 <NA>
## 72 Healthy
## 73 Unhealthy
## 74 Healthy
## 75 Unhealthy
## 76 <NA>
## 77 <NA>
## 78 Healthy
## 79 <NA>
## 80 Healthy
## 81 <NA>
## 82 Healthy
## 83 <NA>
## 84 Healthy
## 85 Unhealthy
## 86 Unhealthy
## 87 <NA>
## 88 Unhealthy
## 89 Healthy
## 90 <NA>
## 91 Unhealthy
## 92 <NA>
## 93 Healthy
## 94 Unhealthy
## 95 <NA>
## 96 <NA>
## 97 <NA>
## 98 Healthy
## 99 <NA>
## 100 <NA>
## 101 Unhealthy
## 102 Healthy
## 103 <NA>
## 104 <NA>
## 105 <NA>
## 106 <NA>
## 107 <NA>
## 108 Unhealthy
## 109 Healthy
## 110 Unhealthy
## 111 <NA>
## 112 <NA>
## 113 Healthy
## 114 Unhealthy
## 115 Healthy
## 116 Healthy
## 117 Unhealthy
## 118 Healthy
## 119 Unhealthy
## 120 Unhealthy
## 121 Healthy
## 122 <NA>
## 123 Healthy
## 124 <NA>
## 125 <NA>
## 126 Unhealthy
## 127 Healthy
## 128 Healthy
## 129 <NA>
## 130 Unhealthy
## 131 <NA>
## 132 Unhealthy
## 133 <NA>
## 134 Unhealthy
## 135 <NA>
## 136 Unhealthy
## 137 Healthy
## 138 Unhealthy
## 139 Healthy
## 140 Healthy
## 141 <NA>
## 142 Unhealthy
## 143 Healthy
## 144 Healthy
## 145 Unhealthy
## 146 <NA>
## 147 Unhealthy
## 148 Healthy
## 149 UnhealthyVisualize sample tree
Fit a single recursive partitioning or classification tree. Followed instructions from this youtube video.
Troubleshooting
Error in randomForest.default(m, y, …) : Need at least two classes to do classification.
I may be misunderstanding this error, but I think it is referring to the response variable?
The documentation here describes the error prompt when: if (classRF && !addclass && length(unique(y)) < 2) stop(“Need at least two classes to do classification.”)
It is possible some of the NA or -9999 values are causing issues.
We can try imputing the data, however this requires us to remove columns with more than 53 factors, which probably makes sense anyway.
Removing factors with more than 53 levels didn’t resolve the error from the randomForest command, but it did allow us to use the rfImpute command to impute our data.
Wow it actually worked if the data is imputed.